Predicting movie sales revenue using online reviews

With the rapid development of E-commerce, more and more online reviews for products and services are created, which form an important source of information for both sellers and customers. Research on sentiment and opinion mining for online review analysis has attracted increasingly more attention because such study helps leverage information from online reviews for potential economic impact. In this paper, we apply sentiment analysis and machine learning methods to study the relationship between the online reviews for a movie and the movie's box office revenue performance. We show that a simplified version of the sentiment-aware autoregressive model proposed in [5] can produce very good accuracy for predicting the box office sale using online review data. Our simplified version considers only positive and negative sentiments, and uses a very simple set of features with 14 affective key words for representing the sentiments in a review. In this way we obtain a simpler model which could be more efficient to train and use. Experiments indicate that the autoregressive model using both review sentiment data and the previous days' sale data results in higher accuracy than just using previous sale data alone. In addition, we create a classification model using Naïve Bayes Classifier for predicting the trend of the box office revenue from the review sentiment data.